toxic-bert text toxicity classifier (6 labels)

Add to the body of POST /v1/apps/{slug}/releases (or a release session). An unknown or withdrawn model is refused with a 400 naming it; the app page then shows "downloads 106 MB · runs on your device" and /models.txt carries the attribution.

{
  "models": [
    {
      "id": "toxic-bert-q8",
      "revision": "65cbc260"
    }
  ]
}

Streams with progress, verifies the SHA-256 against the catalogue, keeps a durable copy in the app's Cache API and reports whether the bytes came from cache or the network.

<script src="/sdk.js"></script>  <!-- vendored from https://skillsafe.ai/apps-sdk/v1.js -->

const ss = SkillSafe.init({ slug: "your-app" });
const caps = await ss.models.capabilities();        // { webgpu, wasm, wasmSimd, storage }
const bytes = await ss.models.load("toxic-bert-q8@65cbc260", "onnx/model_quantized.onnx", {
  onProgress: (p) => (bar.style.width = Math.round(p.ratio * 100) + "%"),
});                                                   // ArrayBuffer — SHA-256 verified, cached

// Later visits: await ss.models.status("toxic-bert-q8@65cbc260")  → { cached: [...], missing: [] }
// Background prefetch on a landing page: ss.models.warm("toxic-bert-q8@65cbc260")

The runtime itself ships in your bundle as a vetted {path, sha256} reference — only the weights come from the registry. Pass the bytes in; do not re-fetch by URL.

import { env, pipeline } from "./transformers.min.js";
env.allowLocalModels = true;
env.localModelPath = "/models/";                   // ship config.json + tokenizer.json at /models/toxic-bert-q8/
env.allowRemoteModels = true;                      // only the weights fall through to the registry
env.remoteHost = "https://models.skillsafe.ai/";
env.remotePathTemplate = "{model}@{revision}/";    // → https://models.skillsafe.ai/toxic-bert-q8@65cbc260/onnx/model_quantized.onnx

const pipe = await pipeline("text-classification", "toxic-bert-q8", {
  revision: "65cbc260",
  dtype: "q8",
  device: "webgpu",
});

Immutable, credential-free, Access-Control-Allow-Origin: *, range requests honoured. The host refuses requests carrying a foreign Origin; a plain curl is fine.

https://models.skillsafe.ai/toxic-bert-q8@65cbc260/onnx/model_quantized.onnx

curl -sSL -o model_quantized.onnx "https://models.skillsafe.ai/toxic-bert-q8@65cbc260/onnx/model_quantized.onnx"
shasum -a 256 model_quantized.onnx   # 620012c9bed13e3c58b9c959d160d955ff033a1a27528212b9da5b0aa4ac3f73

SkillSafe's copy on Hugging Face — the same bytes (the SHA-256 on each file page matches the hash above), plus manifest.json with the upstream commit, recipe and toolchain, the parity reference tensors and a model card. Use it directly for your own site or notebook. A SkillSafe app must load from the registry: its CSP allows models.skillsafe.ai only, and that copy is what the SDK verifies, the browser shares across apps and the app page discloses. SkillSafe keeps hosting its own copies and the API either way.

// Outside SkillSafe apps only: app hosts allow connect-src models.skillsafe.ai, not huggingface.co.
import { pipeline } from "@huggingface/transformers";
const pipe = await pipeline("text-classification", "skillsafe-ai/toxic-bert", { revision: "881c89217e0c5871cf67ffe8ef08453ea016a0ba", device: "webgpu" });

https://huggingface.co/skillsafe-ai/toxic-bert/resolve/881c89217e0c5871cf67ffe8ef08453ea016a0ba/onnx/model_quantized.onnx